scholarly journals Text Polarity Detection using Multiple Supervised Machine Learning Algorithms

2020 ◽  
Vol 9 (3) ◽  
pp. 1612-1618
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Large Scale ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
The Public ◽  
Social Media Platforms ◽  
Day By Day

Sentiment analysis is the classifying of a review, opinion or a statement into categories, which brings clarity about specific sentiments of customers or the concerned group to businesses and developers. These categorized data are very critical to the development of businesses and understanding the public opinion. The need for accurate opinion and large-scale sentiment analysis on social media platforms is growing day by day. In this paper, a number of machine learning algorithms are trained and applied on twitter datasets and their respective accuracies are determined separately on different polarities of data, thereby giving a glimpse to which algorithm works best and which works worst..

scholarly journals A Review of Machine Learning Approach for Twitter Sentiment Analysis

2021 ◽  
Vol 24 (4) ◽  
pp. 52-58
Author(s):  
Mohammed W. Habib ◽  
◽  
Zainab N. Sultani ◽  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Comparative Study ◽  
Sentiment Analysis ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Learning Approach ◽  
Textual Data ◽  
Machine Learning Approach ◽  
Social Media Platforms

One of the active sciences or studies whose importance is rising is the science of sentiment analysis. The reason is due to the increasing sources of data that require investigation. Among the most valuable sources is Twitter, in addition to Facebook and other social media platforms. The objective of sentiment analysis is to classify sentiment/opinions of users as positive, negative, or neutral from textual data. This analysis is valuable for many applications that require understanding people's or users' opinions and emotions about a particular topic, product, or service. Several researchers tackle the problem of sentiment analysis using machine learning algorithms. In this paper, a comparative study is presented of various researches conducted a sentiment analysis on social media and especially on Tweets. The survey carried out in this paper provides an overview of preprocessing steps, machine learning algorithms, and approaches used for sentiment classification during the period 2015-2020.

scholarly journals Towards scaling Twitter for digital epidemiology of birth defects

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Ari Z. Klein ◽  
Abeed Sarker ◽  
Davy Weissenbacher ◽  
Graciela Gonzalez-Hernandez
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Language Processing ◽  
Birth Defects ◽  
Birth Defect ◽  
Learning Algorithms ◽  
Class Imbalance ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Svm Classifier

Abstract Social media has recently been used to identify and study a small cohort of Twitter users whose pregnancies with birth defect outcomes—the leading cause of infant mortality—could be observed via their publicly available tweets. In this study, we exploit social media on a larger scale by developing natural language processing (NLP) methods to automatically detect, among thousands of users, a cohort of mothers reporting that their child has a birth defect. We used 22,999 annotated tweets to train and evaluate supervised machine learning algorithms—feature-engineered and deep learning-based classifiers—that automatically distinguish tweets referring to the user’s pregnancy outcome from tweets that merely mention birth defects. Because 90% of the tweets merely mention birth defects, we experimented with under-sampling and over-sampling approaches to address this class imbalance. An SVM classifier achieved the best performance for the two positive classes: an F1-score of 0.65 for the “defect” class and 0.51 for the “possible defect” class. We deployed the classifier on 20,457 unlabeled tweets that mention birth defects, which helped identify 542 additional users for potential inclusion in our cohort. Contributions of this study include (1) NLP methods for automatically detecting tweets by users reporting their birth defect outcomes, (2) findings that an SVM classifier can outperform a deep neural network-based classifier for highly imbalanced social media data, (3) evidence that automatic classification can be used to identify additional users for potential inclusion in our cohort, and (4) a publicly available corpus for training and evaluating supervised machine learning algorithms.

Application Based Cigarette Detection on Social Media Platforms Using Machine Learning Algorithms

2021 ◽  
pp. 68-80
Author(s):  
Muhammad Umer Hashmi ◽  
Ngoc Duy Nguyen ◽  
Michael Johnstone ◽  
Kathryn Backholer ◽  
Asim Bhatti
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Social Media Platforms

Wearable IoT intelligent recommender framework for a smarter healthcare approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mona Bokharaei Nia ◽  
Mohammadali Afshar Kazemi ◽  
Changiz Valmohammadi ◽  
Ghanbar Abbaspour
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Learning Algorithms ◽  
Wearable Devices ◽  
Machine Learning Algorithms ◽  
Content Type ◽  
Iot Devices ◽  
The Right ◽  
Media Sentiment

PurposeThe increase in the number of healthcare wearable (Internet of Things) IoT options is making it difficult for individuals, healthcare experts and physicians to find the right smart device that best matches their requirements or treatments. The purpose of this research is to propose a framework for a recommender system to advise on the best device for the patient using machine learning algorithms and social media sentiment analysis. This approach will provide great value for patients, doctors, medical centers, and hospitals to enable them to provide the best advice and guidance in allocating the device for that particular time in the treatment process.Design/methodology/approachThis data-driven approach comprises multiple stages that lead to classifying the diseases that a patient is currently facing or is at risk of facing by using and comparing the results of various machine learning algorithms. Hereupon, the proposed recommender framework aggregates the specifications of wearable IoT devices along with the image of the wearable product, which is the extracted user perception shared on social media after applying sentiment analysis. Lastly, a proposed computation with the use of a genetic algorithm was used to compute all the collected data and to recommend the wearable IoT device recommendation for a patient.FindingsThe proposed conceptual framework illustrates how health record data, diseases, wearable devices, social media sentiment analysis and machine learning algorithms are interrelated to recommend the relevant wearable IoT devices for each patient. With the consultation of 15 physicians, each a specialist in their area, the proof-of-concept implementation result shows an accuracy rate of up to 95% using 17 settings of machine learning algorithms over multiple disease-detection stages. Social media sentiment analysis was computed at 76% accuracy. To reach the final optimized result for each patient, the proposed formula using a Genetic Algorithm has been tested and its results presented.Research limitations/implicationsThe research data were limited to recommendations for the best wearable devices for five types of patient diseases. The authors could not compare the results of this research with other studies because of the novelty of the proposed framework and, as such, the lack of available relevant research.Practical implicationsThe emerging trend of wearable IoT devices is having a significant impact on the lifestyle of people. The interest in healthcare and well-being is a major driver of this growth. This framework can help in accelerating the transformation of smart hospitals and can assist doctors in finding and suggesting the right wearable IoT for their patients smartly and efficiently during treatment for various diseases. Furthermore, wearable device manufacturers can also use the outcome of the proposed platform to develop personalized wearable devices for patients in the future.Originality/valueIn this study, by considering patient health, disease-detection algorithm, wearable and IoT social media sentiment analysis, and healthcare wearable device dataset, we were able to propose and test a framework for the intelligent recommendation of wearable and IoT devices helping healthcare professionals and patients find wearable devices with a better understanding of their demands and experiences.

scholarly journals Identification and Detection of Cyberbullying on Facebook Using Machine Learning Algorithms

2021 ◽  
Vol 23 (4) ◽  
pp. 1-21
Author(s):  
Nureni Ayofe AZEEZ ◽  
Sanjay Misra ◽  
Omotola Ifeoluwa LAWAL ◽  
Jonathan Oluranti
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Chi Square ◽  
Social Media Platforms ◽  
Bayes Algorithm ◽  
Use Of Social Media

The use of social media platforms such as Facebook, Twitter, Instagram, WhatsApp, etc. have enabled a lot of people to communicate effectively and frequently with each other and this has enabled cyberbullying to occur more frequently while using these networks. Cyberbullying is known to be the cause of some serious health issues among social media users and creating a way to identify and detect this holds significant importance. This paper takes a look at unique features gotten from the Facebook dataset and develops a model that identifies and detect cyberbullying posts by applying machine learning algorithms (Naïve Bayes Algorithm and K-Nearest Neighbor). The project also uses a feature selection algorithm namely x2 test (Chi-Square test) to select important features which can improve the performance of the classifiers and decrease classification time. The result of this paper tends to detect cyberbullying in Facebook with a high degree of accuracy and also improve the performance of the machine learning classifiers.

scholarly journals Machine Learning Algorithms in Social Media: the Emergence of a Split Subject?

2021 ◽  
Vol 2 (1) ◽  
Author(s):  
Keldt Schoeman
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Moral Agency ◽  
Industrial Revolution ◽  
Learning Algorithms ◽  
Physical Reality ◽  
Machine Learning Algorithms ◽  
Social Actions ◽  
Social Media Platforms ◽  
Scale Usage

Machine learning algorithms are the most common way in which most people interact with artificial intelligence. Wide scale usage of Machine learning has grown dramatically during the last decade, particularly within social media platforms. Considering the almost three billion monthly active users at Facebook and that most of their services rely heavily on machine learning, the aim of this essay is to investigate some of the social and moral implications of ML algorithms employed in social media. Guided by the adage ‘we shape our tools and then they shape us’ the common thread among several varied effects of social media was the outsourcing of important social actions from our physical reality to a virtual one. And, with current ML algorithms being successfully utilised to increase user time expenditure, social media platforms are likely to operate as an amplifier of social media effects i.e., greater time expenditure leads to greater amounts of important social actions outsourced to virtual reality. Now, considering that such extraordinary change as could be wrought by a fourth industrial revolution has historically been accompanied by change in the philosophical subject, it is not unreasonable to consider the possibility that change is occurring once more. Yet, I posit the view that we are currently in an intermediary phase between the physical and virtual realities, that we stand today as split subjects. For, while devices like our phones, consoles, watches and computers mean we are always on, many important social actions remain in the physical real. Though, even the effects of a partial transformation of the subject are substantial, as the kind of splitting many of us do today is reminiscent of compartmentalization, a psychologically significant coping mechanism known for its corrosion of moral agency. As such, with a potentially transient contemporary subject and a variety of associated effects the split subject is rich ground for further research.

Automatic sentiment analysis of public opinion on nuclear energy

Kerntechnik ◽  
2022 ◽  
Vol 0 (0) ◽  
Author(s):  
Hong Xu ◽  
Tao Tang ◽  
Baorui Zhang ◽  
Yuechan Liu
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Nuclear Energy ◽  
Opinion Mining ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Innovative Technology ◽  
The Public

Abstract Opinion mining and sentiment analysis based on social media has been developed these years, especially with the popularity of social media and the development of machine learning. But in the community of nuclear engineering and technology, sentiment analysis is seldom studied, let alone the automatic analysis by using machine learning algorithms. This work concentrates on the public sentiment mining of nuclear energy in German-speaking countries based on the public comments of nuclear news in social media by using the automatic methodology, since compared with the news itself, the comments are closer to the public real opinions. The results showed that majority comments kept in neutral sentiment. 23% of comments were in positive tones, which were approximate 4 times those in negative tones. The concerning issues of the public are the innovative technology development, safety, nuclear waste, accidents and the cost of nuclear power. Decision tree, random forest and long short-term memory networks (LSTM) are adopted for the automatic sentiment analysis. The results show that all of the proposed methods can be applied in practice to some extent. But as a deep learning algorithm, LSTM gets the highest accuracy approximately 85.6% with also the best robustness of all.

Sign in / Sign up

Export Citation Format

Share Document